mlsanityData to 14 Oct 2026

Enhancing Retrieval and Managing Retrieval: A Four-Module Synergy for Improved Quality and Efficiency in RAG Systems

arXiv 2407.10670 ↗First posted 15 Jul 2024cs.CL cs.AIcited by 15

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

Abstract (arXiv)

Retrieval-augmented generation (RAG) techniques leverage the in-context learning capabilities of large language models (LLMs) to produce more accurate and relevant responses. Originating from the simple 'retrieve-then-read' approach, the RAG framework has evolved into a highly flexible and modular paradigm. A critical component, the Query Rewriter module, enhances knowledge retrieval by generating a search-friendly query. This method aligns input questions more closely with the knowledge base. Our research identifies opportunities to enhance the Query Rewriter module to Query Rewriter+ by generating multiple queries to overcome the Information Plateaus associated with a single query and by rewriting questions to eliminate Ambiguity, thereby clarifying the underlying intent. We also find that current RAG systems exhibit issues with Irrelevant Knowledge; to overcome this, we propose the Knowledge Filter. These two modules are both based on the instruction-tuned Gemma-2B model, which together enhance response quality. The final identified issue is Redundant Retrieval; we introduce the Memory Knowledge Reservoir and the Retriever Trigger to solve this. The former supports the dynamic expansion of the RAG system's knowledge base in a parameter-free manner, while the latter optimizes the cost for accessing external knowledge, thereby improving resource utilization and response efficiency. These four RAG modules synergistically improve the response quality and efficiency of the RAG system. The effectiveness of these modules has been validated through experiments and ablation studies across six common QA datasets. The source code can be accessed at https://github.com/Ancientshi/ERM4.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 24 of its 27 references that are in the map. First posted on arXiv 15 Jul 2024.

Builds on

24 of 27 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023RETA-LLM: A Retrieval-Augmented Large Language Model Toolkit8 Jun

Other references · 23

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  5. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  6. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  7. 2015A large annotated corpus for learning natural language inferencecited by 1,847
  8. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  9. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  10. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  11. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 876
  12. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
11 more
  1. 2020AmbigQA: Answering Ambiguous Open-domain Questionscited by 390
  2. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 346
  3. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 318
  4. 2022RARR: Researching and Revising What Language Models Say, Using Language Modelscited by 287
  5. 2017Constructing Datasets for Multi-hop Reading Comprehension Across Documentscited by 190
  6. 2023Answering Questions by Meta-Reasoning over Multiple Chains of Thoughtcited by 87
  7. 2022Shortcut Learning of Large Language Models in Natural Language Understandingcited by 85
  8. 2021Temporal Adaptation of BERT and Performance on Downstream Document Classification: Insights from Social Mediacited by 51
  9. 2023Tree of Clarifications: Answering Ambiguous Questions with Retrieval-Augmented Large Language Modelscited by 43
  10. 2023Asking Clarification Questions to Handle Ambiguity in Open-Domain QAcited by 26
  11. 2023From Classification to Generation: Insights into Crosslingual Retrieval Augmented ICLcited by 17

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 10; 2026: 3.

15 papers.

Sort:

By area:

  1. 2025PersonaX: A Recommendation Agent Oriented User Modeling Framework for Long Behavior Sequencecited by 33
  2. 2025Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoningcited by 29
  3. 2025AttentionRAG: Attention-Guided Context Pruning in Retrieval-Augmented Generationcited by 19
  4. 2025Resisting Contextual Interference in RAG via Parametric-Knowledge Reinforcementcited by 11
  5. 2024Multi-OphthaLingua: A Multilingual Benchmark for Assessing and Debiasing LLM Ophthalmological QA in LMICscited by 10
  6. 2025Graph-Augmented Reasoning: Evolving Step-by-Step Knowledge Graph Retrieval for LLM Reasoningcited by 8
  7. 2025Context-Guided Dynamic Retrieval for Improving Generation Quality in RAG Modelscited by 8
  8. 2024A Learnable Agent Collaboration Network Framework for Personalized Multimodal AI Search Enginecited by 5
  9. 2025A Survey on Foundation Models for Personalized Federated Intelligencecited by 3
  10. 2025Dynamic Collaboration of Multi-Language Models based on Minimal Complete Semantic Unitscited by 2
  11. 2025GDLLM: A Global Distance-aware Modeling Approach Based on Large Language Models for Event Temporal Relation Extractioncited by 2
  12. 2026Test-Time Strategies for More Efficient and Accurate Agentic RAGcited by 1
3 more
  1. 2025Improving Document Retrieval Coherence for Semantically Equivalent Queriescited by 0
  2. 2026Structure-Aware RAG: Structured Retrieval Augmented Generation from Noisy Data for Conversational Agentscited by 0
  3. 2026CLEAR: Cross-Source Evidence Adjudication for Large Language Models in Medicinecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Enhancing Retrieval-Augmented Generation: A Study of Best Practices
  2. 2025Dynamic and Parametric Retrieval-Augmented Generation
  3. 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generation
  4. 2024Toward Optimal Search and Retrieval for RAG
  5. 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning
  6. 2025Investigating the Robustness of Retrieval-Augmented Generation at the Query Level
  7. 2025Fast or Better? Balancing Accuracy and Cost in Retrieval-Augmented Generation with Flexible User Control
  8. 2025Know3-RAG: A Knowledge-aware RAG Framework with Adaptive Retrieval, Generation, and Filtering